This repo contains the Optical Character Recognition (OCR) project as part of my data science portfolio. I have built an OCR to extract text from shopping receipts for further analysis, using two popular methods below:
- Tesseract-OCR
- OCR.space
Besides extracting text from shopping receipts, there are other interesting applications as well, such as extracting text from medical reports for further analysis. It is part of the Data Collection / Acquisition process in the overall Data Science Workflow. If you have any feedback for this project, feel free to contact me via my LinkedIn or GitHub Pages.